Full Fine-Tuning (FFT) on SageMaker AI Serverless Model Customization
Amazon SageMaker AI Serverless Model Customization now supports Full Fine-Tuning (FFT).
Amazon SageMaker AI Serverless Model Customization now supports Full Fine-Tuning (FFT).
The Amazon SageMaker JumpStart Model Leaderboard compares 70+ foundation models side by side on quality, speed, and cost, directly in SageMaker Studio. Learn what the leaderboard shows, how AWS benchmarks models, and how to go from a shortlist to a deployed model.
The biggest cost lever in a generative AI system is whether you call a model at all. Learn how to decide whether each workflow step needs a model, and map each option to AWS: deterministic code, a constrained decision call, or a right-sized model on Amazon Bedrock.
Running Amazon Bedrock across many accounts shows you the bill but not what happened inside each call.
Claude Fable 5.2 and Claude Mythos 5.2 are now available on Amazon Bedrock and Claude Platform on AWS. Learn what's new in both models, why Fable 5.2 matters for your technical workloads, and how to get started building with it on Amazon Bedrock.
Learn how Amazon Marketplace evaluates A+ Content quality at scale on Amazon SageMaker AI by rendering each product page as a single snapshot, scoring it with a vision-language model fused with OCR readability signals in a CatBoost classifier, and using SHAP to turn each…
This post presents a five-stage operating model for managing Amazon Bedrock cost: attribute every dollar to an owner, make every request observable, enforce budgets, optimize platform defaults, and operate a review cadence. Written for FinOps and platform engineering teams.
Property Finder found that 96.8% of their vision-AI evaluation labels were inherited from the incumbent model, hiding its true accuracy.
In this post, we show how Exowatt used Amazon SageMaker AI serverless model customization to build a repeatable AI pipeline that produces task-specific fine-tuned models for two deployment targets, edge and cloud, achieving higher accuracy than frontier models at up to 49x…
Learn how i14 trained and served Laplace 3B, a linear attention model, on AWS Trainium2 using native PyTorch.
Learn how we fine-tuned GPT-OSS-20B for multilingual reasoning on Amazon SageMaker HyperPod, and how to decide between supervised fine-tuning (SFT) and reinforcement learning with GRPO.
Amazon Bedrock now supports structured JSON Schema outputs for all Anthropic Claude models, eliminating custom parsing needs.
Amazon SageMaker JumpStart onboarded over 100 new models from 30 providers in the first three quarters of 2026, enhancing its Model Hub and Hugging Face integration.
TwelveLabs Pegasus 1.5 is now available in Amazon Bedrock. The model processes up to two hours of video, creating structured, timestamped metadata.
Deepgram ported its Nova-3 speech-to-text model to AWS Trainium2 for batch inference, utilizing the AWS Neuron stack and kernel-level tuning.
A new push-based NIXL connector in vLLM for disaggregated LLM inference improves TTFT by up to 3x and TPOT by 30% through KV cache transfer coordination.
Bi-directional KV cache transfer in vLLM reduces time to first token by up to 1.6x for Qwen3-32B and 3.3x for GLM-5-FP8 in multi-turn agentic workloads.
Reflection AI has released Reflection Beam, an open-weight model for agentic coding and long-horizon tasks, deployable on AWS.
Meta's coding-optimized Muse Spark Open model is now available in Amazon SageMaker JumpStart, allowing deployment within an AWS account.
Grok 4.7 is available on Amazon Bedrock; the post demonstrates building and evaluating tool-calling agents for long-horizon reasoning tasks.
Learn how to run OpenAI GPT-6 Sol, Luna, and Astra on Amazon Bedrock through global cross-Region inference from Singapore, Jakarta, Thailand, Malaysia, and Taipei.
Learn how to deploy decision models with llama.cpp on Amazon SageMaker AI, using OpenAI-compatible chat completions and extending the runtime to return probabilities.
Learn how to deploy one large language model across two GPU nodes on Amazon EKS using the multi-node Ray LLM Deep Learning Containers with separate prefill and decode nodes.
Amazon Bedrock, Bedrock AgentCore, and Strands received broader model choice, faster agents, and automated knowledge base syncing in September 2026.
Postman and AWS shared architectural patterns for running Agent Mode for 40 million developers on Amazon Bedrock, focusing on tool control, schema exposure, and context.
Claude Haiku 5.5 is now available on Amazon Bedrock and Claude Platform on AWS. It is Anthropic's fastest and most efficient model in the Claude 5.5 family, designed for subagents and cost-sensitive tasks.
Qlik built Qlik Answers on Amazon Bedrock using a multi-agent architecture and Amazon Bedrock Guardrails to deliver trusted answers across enterprise data.
AWS Bedrock now offers Z.ai's GLM 5.3 model, a 753B-parameter model optimized for coding and agentic tasks.
AWS added Anthropic Claude Opus 5.5 and Sonnet 5.5 to Amazon Bedrock, and Claude Code for development on regulated and ITAR workloads.